More RLHF, More Trust? On The Impact of Human Preference Alignment On Language Model Trustworthiness.
Aaron J. LiSatyapriya KrishnaHimabindu LakkarajuPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- speech recognition
- personality traits
- n gram
- document retrieval
- test collection
- information retrieval
- trust propagation
- retrieval model
- language modelling
- context sensitive
- query expansion
- ad hoc information retrieval
- language models for information retrieval
- query terms
- statistical language models
- document length
- smoothing methods
- language model for information retrieval
- document ranking
- trust model
- mixture model
- relevance model
- consumer trust
- trust relationships
- multiword
- word error rate
- language modeling framework
- vector space model
- retrieval effectiveness
- information extraction